|
mxnet
|
implementation of GPU host code More...


Go to the source code of this file.
Namespaces | |
| mshadow | |
| overloaded + operator between half_t and bf16_t | |
Functions | |
| template<> | |
| void | mshadow::InitTensorEngine< gpu > (int dev_id) |
| template<> | |
| void | mshadow::ShutdownTensorEngine< gpu > (void) |
| template<> | |
| void | mshadow::SetDevice< gpu > (int devid) |
| template<int dim, typename DType > | |
| void | mshadow::AllocSpace (Tensor< gpu, dim, DType > *obj, bool pad=MSHADOW_ALLOC_PAD) |
| CPU/CPU: allocate space for CTensor, according to the shape in the obj this function is responsible to set the stride_ in each obj.shape. More... | |
| template<int dim, typename DType > | |
| void | mshadow::FreeSpace (Tensor< gpu, dim, DType > *obj) |
| CPU/GPU: free the space of tensor, will set obj.dptr to NULL. More... | |
| template<typename A , typename B , int dim, typename DType > | |
| void | mshadow::Copy (Tensor< A, dim, DType > _dst, Tensor< B, dim, DType > _src, cudaMemcpyKind kind, Stream< gpu > *stream) |
| template<int dim, typename DType > | |
| void | mshadow::Copy (Tensor< cpu, dim, DType > dst, const Tensor< gpu, dim, DType > &src, Stream< gpu > *stream=NULL) |
| copy data from one tensor to another, with same shape More... | |
| template<int dim, typename DType > | |
| void | mshadow::Copy (Tensor< gpu, dim, DType > dst, const Tensor< gpu, dim, DType > &src, Stream< gpu > *stream=NULL) |
| copy data from one tensor to another, with same shape More... | |
| template<int dim, typename DType > | |
| void | mshadow::Copy (Tensor< gpu, dim, DType > dst, const Tensor< cpu, dim, DType > &src, Stream< gpu > *stream=NULL) |
| copy data from one tensor to another, with same shape More... | |
implementation of GPU host code
1.8.13